Sr. Software Engineer, AI

NinjaTrader•Chicago, IL

5d•Hybrid

About The Position

NinjaTrader is heavily investing in AI, not just as a product feature, but as a company-wide force multiplier. We are seeking an internal, forward-deployed AI Engineer to accelerate the adoption of agentic AI across various departments including Engineering, Operations, Customer Experience, Data, Finance, and more. This role will own the AI infrastructure that supports every team, with the expectation that the work completed in the first year will save thousands of hours annually through the creation of over 50 new AI agents. The engineer will embed with internal teams to identify high-leverage automation opportunities and manage them from discovery and simplification through to build, deployment, and adoption. The role involves scoping problems with non-technical stakeholders in the morning and shipping production infrastructure in the afternoon, measuring success by hours unlocked and cycle time reduced rather than stories closed.

Requirements

5+ years of production software engineering experience, primarily in Python or TypeScript. Go is a plus.
Production LLM application experience with Anthropic or OpenAI SDKs, including agents, structured outputs, tool use, RAG, evals, and batch processing – demonstrated through shipped products, not just demos.
Forward-deployed instinct, demonstrated through experience in engineering, developer relations, or solutions engineering.
Strong evaluation discipline with the ability to define and defend exit criteria using tools like LangSmith, Braintrust, or equivalent.
Experience building multi-step tool-using agents with planning, error recovery, and human-in-the-loop design in production environments.
Experience with RAG pipelines, embeddings, hybrid search, and the judgment to determine when retrieval improves outcomes.
Experience building MCP servers, function-calling schemas, and sandboxed execution environments.
Strong understanding of token budgets, model tier trade-offs, and AI cost/latency optimization strategies.
Experience integrating REST APIs, GraphQL, webhooks, OAuth/SAML authentication (especially Okta), and event-driven architectures.
Cloud-native engineering experience with GCP or AWS, including Terraform, containers, secrets management, logging, metrics, and alerting.
Strong SQL and data engineering experience with modern warehouses, ETL/ELT pipelines, schema design, and data-quality monitoring.
Ability to work cross-functionally and translate ambiguous business problems into production-ready AI systems.
Strong communication skills with both technical and non-technical stakeholders.

Nice To Haves

Trading industry, fintech, or capital markets experience.
Futures trading knowledge.
Experience with LangChain, LlamaIndex, or similar orchestration frameworks.
Familiarity with observability tooling such as OpenTelemetry, Prometheus, and Grafana.
Contributions to open-source AI or developer tooling projects.

Responsibilities

Design and build multi-step agentic workflows in Python and TypeScript, including planning loops, tool dispatch, error recovery, and human-in-the-loop checkpoints for critical decisions.
Develop production LLM applications using Anthropic and OpenAI SDKs, incorporating prompt engineering, structured outputs, tool/function calling, prompt caching, and batch processing.
Build and maintain RAG pipelines, including embedding generation, vector/hybrid search, and knowledge base ingestion, with a focus on determining when retrieval genuinely aids outcomes versus introducing noise.
Own end-to-end evaluation discipline: define offline evaluation sets, conduct A/B experiments on model changes, build regression suites, and articulate clear 'good enough' exit criteria using tools like LangSmith or Braintrust.
Drive cost and latency optimization through strategies like token budget management, appropriate model tier selection (e.g., Haiku/Sonnet/Opus and GPT equivalents), and scalable caching.
Build MCP servers and function-calling connectors to provide agents with reliable, schema-governed access to internal tools, APIs, and data sources (Jira, CRM, Slack, internal services, etc.).
Implement and maintain production integrations using REST, GraphQL, webhooks, and event-driven patterns (queues, Pub/Sub), ensuring proper idempotency, retry logic, and backfill support.
Wire up OAuth/SAML authentication flows, particularly with Okta, for secure agent-to-service access across internal and third-party systems.
Own cloud infrastructure for AI workloads on GCP using Terraform, GKE/Cloud Run, and secrets management, including immediate implementation of logging, metrics, and alerting.
Build data pipelines to feed AI systems, leveraging strong SQL, modern data warehouses (Athena/BigQuery-class), ETL/ELT processes, schema design, and data-quality monitoring.
Partner with internal teams across Engineering, Operations, Customer Support, Data, and Finance to identify and implement high-leverage automation opportunities using agentic AI.
Create reusable libraries, SDKs, and internal tooling to enable teams to extend AI capabilities without starting from scratch.
Act as a technical advisor and embedded engineer, translating ambiguous business problems into well-scoped AI systems with clear success metrics.
Instrument and monitor deployed agents in production, taking on-call responsibilities and treating reliability as a core feature.