Power Systems Distribution Specialist

Pravāh•San Francisco, CA

About The Position

As a Power Systems Distribution Engineer, you will own the power systems modeling and analysis capabilities at the core of Pravāh's grid intelligence platform, spanning both real-time operational analysis and long-term distribution planning. On the operational side, you will build and validate power flow models that compute real-time technical losses, estimate network state from sparse AMI and SCADA measurements, and identify anomalies across distribution feeders serving millions of customers. On the planning side, you will develop simulation workflows for new distribution system design, including capacity expansion, DER interconnection studies, voltage regulation, and contingency analysis, that utilities use to make capital investment decisions. You will work at the intersection of classical power systems engineering and modern software: translating domain expertise into scalable computational workflows, collaborating directly with ML engineers who are building demand and weather forecasting models, and with software engineers who are productionizing your analysis into utility-facing tools. You will also be the domain authority in conversations with utility partners, understanding their operational challenges, data environments, and regulatory contexts across India, the US, and other markets. This is a founding role. You will not be running studies in isolation. You will shape how Pravāh thinks about the grid, define what problems we solve, and build the analytical engine that hundreds of millions of customers ultimately depend on.

Requirements

Bachelor's or Master's degree in Electrical Engineering, Power Systems, or a related technical field.
5+ years of experience in distribution power systems analysis, either at an electric utility, engineering consultancy, grid software vendor, or research institution.
Strong understanding of power system fundamentals: power flow analysis, voltage regulation, short circuit analysis, contingency analysis, power factor correction, and technical loss computation at the distribution level.
Proficiency in at least one power system simulation tool (e.g., CYME, Synergi Electric, PowerFactory, GridLAB-D, OpenDSS, ETAP, or equivalent). We care about your ability to model and reason about distribution systems, not mastery of any single tool.
Hands-on experience working with operational utility datasets, including SCADA, AMI/smart meter data, GIS network models, OMS outage records, or billing/energy accounting data.
Programming proficiency in Python (strongly preferred) or MATLAB, with experience automating power flow studies, data processing pipelines, or analytical workflows. You will be writing code daily, not just clicking through GUI tools.
Experience building or validating distribution network models from real-world utility GIS and asset data, with an understanding of the gap between as-built records and actual network conditions.
Excellent analytical and problem-solving skills, with the ability to work through ambiguous, incomplete data and still produce defensible engineering conclusions.
Strong communication skills, including the ability to explain complex power systems analysis to software engineers, ML researchers, and non-technical stakeholders.

Nice To Haves

Professional Engineer (P.E.) license.
Experience with distribution system state estimation or real-time power flow applications using AMI or SCADA data.
Experience with DER interconnection studies, hosting capacity analysis, or solar/storage impact assessments on distribution networks.
Working knowledge of CIM (IEC 61968/61970) data models and experience with utility data integration or GIS-to-model conversion workflows.
Familiarity with distribution automation (DA), FLISR (fault location, isolation, and service restoration), or advanced distribution management systems (ADMS).
Experience with distribution system planning in emerging markets, particularly India, where challenges include high AT&C losses, partial metering, unbalanced LT networks, and rapid load growth.
Understanding of ML/AI applications in power systems, including demand forecasting, anomaly detection, or probabilistic load modeling, and ability to bridge domain expertise with data science approaches.
Experience in a software product environment, agile development, or working closely with software engineering teams to productionize analytical workflows.
Track record in high-growth or zero-to-one environments where you have defined analytical approaches from scratch rather than following established playbooks.

Responsibilities

Operational Power Flow and Loss Analysis: Build, validate, and maintain distribution power flow models for utility clients, ingesting real-world network topology (GIS, CIM), asset parameters (transformer ratings, conductor impedances, capacitor banks), and operational measurements (AMI, SCADA) to produce accurate steady-state solutions.
Develop and operationalize real-time technical loss computation workflows that run continuously against live or near-live meter data, identifying loss hotspots at the feeder, distribution transformer, and segment level across networks with thousands of nodes.
Design methods for distribution system state estimation from sparse and noisy measurement data, handling the reality of Indian DISCOMs where AMI penetration may be partial, SCADA coverage is inconsistent, and network connectivity records are incomplete or inaccurate.
Build automated validation pipelines that detect data quality issues, topology errors, and measurement inconsistencies before they propagate into power flow results, including cross-referencing GIS asset records against electrical measurements to identify unauthorized connections, phase imbalances, and metering anomalies.
Develop loss disaggregation methodologies that separate technical losses (I²R, transformer core/copper) from commercial losses (theft, metering errors), enabling utilities to target interventions with quantified impact estimates.
Distribution System Planning and Simulation: Develop simulation workflows for new distribution system planning, including capacity expansion studies, feeder routing optimization, transformer sizing, and voltage regulation analysis for greenfield and brownfield scenarios.
Build and run hosting capacity analysis and DER interconnection studies to evaluate the impact of rooftop solar, battery storage, and EV charging on distribution feeders, including voltage rise, reverse power flow, protection coordination, and thermal limits.
Perform contingency analysis and reliability studies, covering N-1 scenarios, fault current calculations, and protection coordination reviews, to support utility investment planning and regulatory filings.
Develop power flow scenarios that model the impact of demand growth, electrification (EV, heat pumps), and DER penetration on existing distribution infrastructure over 5 to 20 year planning horizons.
Support voltage optimization and power factor correction studies, analyzing capacitor placement, voltage regulator settings, and conservation voltage reduction (CVR) opportunities to reduce losses and defer capital upgrades.
Data Ingestion, Normalization and Model Building: Pioneer methods for ingesting and normalizing complex, real-world utility data at scale, including GIS shapefiles and geodatabases, CIM/IEC 61968/61970 models, legacy asset registers, conductor libraries, and heterogeneous naming conventions across different utility systems.
Build automated pipelines that transform raw utility GIS and connectivity data into validated power flow models, handling the messy reality of missing impedance data, incomplete phasing information, incorrect connectivity, and undocumented network modifications.
Develop repeatable model-building workflows that can onboard a new utility client's distribution network (thousands of feeders, millions of nodes) in weeks rather than months, creating the scalable foundation for Pravāh's multi-utility platform.
Work with ML engineers to define feature engineering requirements from power systems data, identifying which network topology features, loading patterns, and voltage profiles are most predictive for demand forecasting and anomaly detection models.
Cross-Functional Collaboration and Domain Leadership: Serve as the deep domain authority for Pravāh's cross-functional team, translating power systems concepts into engineering specifications for software and ML teams, and translating client requirements into feasible analytical workflows.
Lead technical conversations with utility partners, understanding their operational challenges (high AT&C losses, monsoon-related outages, DER integration), data environments (GIS platforms, SCADA systems, billing databases), and regulatory contexts (state electricity regulatory commissions, tariff structures, loss reduction mandates).
Collaborate with ML teams to validate that forecasting models and AI-driven insights are physically consistent with power systems constraints, ensuring demand forecasts, loss estimates, and grid state predictions respect network topology and electrical physics.
Define product requirements and roadmap priorities from a power systems perspective, identifying which analytical capabilities create the most value for utility clients and which technical approaches are feasible at scale.
Lead technical validation of Pravāh's tools against utility-accepted benchmarks, ensuring power flow results, loss calculations, and planning recommendations meet the accuracy and reliability standards that utilities require for operational and regulatory use.