Forward Deployed Engineer

LLR Partners•Philadelphia, PA

6d•Onsite

About The Position

LLR Partners is hiring two Forward Deployed Engineers to build AI-native products that generate real operating leverage across the firm. These products aim to increase AUM per head, decisions per hour, and institutional memory retention. The engineers will collaborate closely with LLR's teams, including Investment, Origination, and the Value Creation Team, and expand to other functions. The role involves shipping agentic workflows, custom web apps, and enterprise knowledge infrastructure from conception to production within weeks. This is a mid-level position offering significant ownership, where the engineer will not just use off-the-shelf AI tools but will build custom MCP servers, reusable Claude Skills, RAG pipelines, and the semantic and judgment layers necessary for trustworthy AI agents at scale.

Requirements

Ability to work in-person in LLR's Philadelphia office.
2-4 years of professional software engineering experience.
At least 1 year of experience shipping production LLM applications, agents, or retrieval systems to real users.
Strong Python skills (async, typing, testing).
Experience with TypeScript, Next.js, or Streamlit for shipping custom web apps and internal tools.
Deep hands-on experience with foundation model APIs and SDKs (Anthropic, OpenAI), including tool use, function calling, structured outputs, and prompt engineering.
Experience building RAG pipelines end-to-end (chunking, embeddings, vector stores like pgvector or Pinecone, retrieval and generation evaluation).
Experience building custom MCP servers and reusable Claude Skills, not just consuming them.
Fluency in Claude and ChatGPT ecosystems (Connectors, Claude Code, Codex, Cowork) and agentic frameworks (LangGraph, PydanticAI, DSPy) deployed in production.
Track record as a forward-deployed, founding, or early engineer on a small, high-ownership team, with experience working directly with non-technical users on real problems.
Experience designing for regulated environments, including data classification, PII handling, scoped access, information barriers, and audit logs for agent actions.

Nice To Haves

Experience within private equity, financial services, consulting, or another regulated, document-heavy environment.
Comfort in an Azure environment, including familiarity with Azure AI Foundry.
Familiarity with modern deployment platforms (Render, Vercel, Supabase).
Experience with Git-based workflows.
Experience building harnesses for agents (using a framework or standing up your own).
Knowledge graph or GraphRAG experience, with a bonus for enterprise search architectures at scale.
Experience communicating technical work to non-technical stakeholders through writing, decks, and live demos.
Flexibility with project management and workflow tools (JIRA, Trello, Linear, Asana, or similar).
Working knowledge of PE-stack data (PitchBook, SourceScrub, Grata, Allvue, Chronograph) and the deal lifecycle (IC memos, LP reporting, fund structures).
Curiosity about and informed perspective on the evolving AI and agent ecosystem.
Awareness of token economics and inference cost (model selection, prompt caching, routing small vs. frontier models by task).
Experience extracting structure from messy documents (PDF parsing, table extraction, meeting transcripts, email threads).
Experience with observability tooling for agents in production (LangSmith, Langfuse, Braintrust, or similar for tracing and debugging).

Responsibilities

Ship AI-native internal products.
Build and own agentic workflows, copilots, and internal tools for investment, origination, investor relations, operations, HR, finance, and the value creation team.
Build the platform layer, including custom MCP servers exposing LLR's data to agents, RAG pipelines (chunking, embeddings, vector stores, retrieval/generation, evals), and reusable Claude Skills that codify LLR patterns.
Ship custom internal web apps using JavaScript, React, or Streamlit for non-technical users, ensuring they are polished, fast, and production-ready.
Contribute to the enterprise knowledge graph and semantic search to consolidate LLR's data into a queryable system.
Build the judgment layer, including LLM-as-judge evaluations, deterministic assertions, guardrails, observability, approval flows, confidence thresholds, and escalation paths to ensure human oversight for agent outputs.
Instrument everything to measure the value of each agent, tracking adoption, usage, and hours returned.
Partner across the firm with deal teams, origination, IR, operations, HR, finance, and the Value Creation Team to identify high-leverage workflows and deliver end-to-end solutions.
Drive AI adoption across the firm through regular trainings, office hours, playbook creation, and user support to make tools habitual.