Ai Engineer

About Supra ITS
Supra ITs builds an enterprise agent platform that customers run in the cloud or on-prem. Admins create and entitle custom agents (prompts, tools, knowledge). End users chat with those agents over documents, SQL, policy RAG, and operational systems (e.G. ticket triage, order audit, product intelligence).The role
You will own agent runtime and AI-adjacent backend: how skills are built, how tools are called, how retrieval and file context work, and how LLM traffic is routed, attributed, and kept safe. You will ship with Test Driven Development, architecture decision records, and story-level acceptance criteria — not notebooks that never reach production.You Will Work Across
LangGraph / Deep Agent graphs (ReAct, multi-step research, custom skills)Tooling: native file/SQL/todo tools, MCP (policy search, Graph files, customer systems)RAG & retrieval: Qdrant collections per agent, hybrid/keyword fallback, knowledge ingest vs chat attachmentsAI Gateway: LiteLLM, model aliases, spend attribution, fail-clear routingProduct surfaces: Agent Chat, Admin Builder, Sandbox, entitlements/deployFrontend (React/TypeScript) is not the primary hire, but you will touch chat/sandbox contracts when the agent loop or upload path changes.What You Will Do
Design and implement agent loops: system prompts, tool selection, state (messages, virtual FS, conversation persistence), streaming SSEAdd or harden tools (MCP and native) with clear failure modes — no silent drops, no leaking secrets in client errorsImprove retrieval quality (chunking, embeddings, hybrid search, citations grounded in tool output)Integrate the LiteLLM gateway: routing, timeouts, streaming, per-agent/skill attributionKeep chat attachments, durable conversation artifacts, and knowledge corpus on the correct stores (they are not the same)Write pytest (and Vitest when you change UI contracts);
trace work to user stories and ADRsPartner with Product, Architect, QA, and UX on sandbox-first proofs before entitle/deploySupport on-prem and dual-cloud constraints: Postgres as source of truth, no “works only on one vendor’s blob store”Must-have Qualifications
Strong Python in production services (FastAPI or similar)Hands-on LLM application work: function/tool calling, RAG, prompt + eval loops — not only wrapping a chatbot widgetComfort with LangChain / LangGraph (or equivalent graph/agent orchestration) and debugging multi-turn tool tracesSolid SQL / Postgres;
you can reason about migrations, RLS, and “this belongs in a row vs object storage”TDD habit: you write the failing test first for services that can lie to users (file extract, persist, authz)Clear written design: you can explain trade-offs (e.G. hydrate files from DB vs S3) to non-research stakeholders[3–5+ years] software engineering, including [1–2+] years shipping LLM featuresNice to have
Vector DBs (Qdrant), embeddings pipelines, hybrid/BM25 + dense retrievalMCP servers or OpenAI-compatible tool catalogsLiteLLM, Azure OpenAI / Anthropic, gateway or router experienceReact/TypeScript (Vite) enough to wire FormData, SSE, and admin sandboxKnowledge graphs / Neo4j (Product Intelligence / Deep Research)Enterprise authz (JWT, RBAC, entitlements), OWASP-minded reviewsDocker/Kubernetes, AWS and/or GCP, on-prem install empathyDomain exposure: manufacturing/distribution, ticketing (ConnectWise-class), policy/audit workflowsWhat This Role Is Not
Training or fine-tuning foundation models as the main jobPure data science / notebook research with no production barPrompt-only “AI consultant” without owning the runtimeHow We Work
Stories → ADRs → TDD implementation → review → QA. Caps and fail-closed behavior are product requirements (e.G. max files per turn, no silent truncate). You will be expected to prove behavior in Admin Sandbox the same way production Chat works.Skills: langchain,sql,python
#J-18808-Ljbffr