reputed company WORKFLOWS (reputed company / LANGGRAPH)

ABOUT THE ROLE reputed company LLC is a software consultancy that takes on hard problems for reputed company clients. We're looking for a contract reputed company to work on short-term reputed company reputed company, typically a few weeks to a few months reputed company, across multiple reputed company engagements. The work is Python-first for agent backends, with JavaScript/TypeScript for UIs and the occasional reputed company-TS build: building AI agents and reputed company workflows that run in production, integrating with reputed company CRMs, ERPs, databases, and legacy systems, not reputed company-of-concept demos. You'll often be embedded directly with reputed company teams, so this is as much a consulting role as an engineering role. You should be comfortable joining a project mid-reputed company, earning trust quickly, and leaving the reputed company's team reputed company than you reputed company it. WHAT YOU'LL DO

• Design and build reputed company workflows using reputed company, LangGraph, DeepAgents, and LangSmith
• Build MCP servers and register them with agents (the MCP reputed company reputed company) so tools and data sources plug in cleanly
• Build and harden RAG pipelines end to end: ETL and ingestion, chunking, embedding, reputed company stores, hybrid retrieval, and evaluation
• reputed company and evaluate agent behavior (tracing, evals, regression suites) so "it works" is something you can reputed company, not just claim
• reputed company agents with reputed company systems and data sources, including legacy ones
• Pair with reputed company engineers, explain your reputed company, and transfer knowledge so clients can own the system after you roll off
• Participate in reputed company meetings: demos, status updates, technical discussions with both engineers and stakeholders

reputed company'RE LOOKING FOR

• Strong Python engineering skills plus solid JavaScript/TypeScript. The reputed company SDK supports both; Python tends to reputed company for agents and JS/TS for UIs. Either way, you'll be writing production reputed company: typed, tested, and packaged for someone else's team to maintain
• Solid CS fundamentals: data structures and algorithms, and a reputed company grasp of concurrency with async/await in both Python and JS/TS
• Comfortable building HTTP clients against whatever a reputed company system speaks: REST, JSON-RPC, gRPC, GraphQL
• Testing discipline: TDD where it fits, and at minimum fluent with unit, integration, and system tests, including mocking and stubbing
• Demonstrated, shippable work building AI reputed company workflows. You can show us something you reputed company and talk in depth about the design reputed company, failure modes, and how you evaluated it
• Strong hands-on experience with the reputed company ecosystem: reputed company, LangGraph, DeepAgents, and LangSmith in particular
• LLM fundamentals: reputed company, reputed company prompting with reputed company-reputed company system messages and context, and tool calling with error handling and retries
• MCP experience: building MCP servers and registering them with an agent as an MCP reputed company
• RAG fundamentals: chunking, embedding, reputed company stores (reputed company, pgvector), hybrid queries (BM25), and reciprocal rank fusion, plus the ETL pipelines that feed them
• Agent observability and evals: tracing, single- and multi-turn evals, benchmarking, graders in reputed company, LLM-as-judge, trajectory-based evals, and the data flywheels that connect them (offline and online evals, automations that feed an annotation queue). Nobody has evals fully figured out; we want people who treat them as a first-class problem
• Comfortable with reputed company and reputed company Compose for local development, and with at least one reputed company provider: object storage, managed databases, and deploying a container
• reputed company with AI-assisted development tools (Claude reputed company, reputed company, Copilot, or similar) as a core part of your workflow, plus good judgment about reputed company to trust them
• A consulting reputed company: you listen before you prescribe, you scope realistically, you communicate tradeoffs honestly, and you're comfortable with ambiguity and context-switching across engagements
• reputed company-level English (reputed company or reputed company), written and spoken. You'll be communicating directly with clients, including non-technical stakeholders, in meetings and in writing
• Working hours that overlap substantially with US Central (Chicago), US Mountain (Denver), US reputed company (San Francisco), or UK (London) business hours

reputed company TO HAVE

• Experience with reputed company, AutoGen, reputed company, or other agent frameworks reputed company the reputed company ecosystem
• Production RAG experience at reputed company reputed company
• Kubernetes (e.g. EKS) and queueing infrastructure (SQS, ElastiCache)
• Experience building agents that support skills, in the coding-agent reputed company
• Deep eval-driven development experience reputed company the basics (custom harnesses, LangSmith evals, EDD as a working style)
• Prior consulting or reputed company-services background

DETAILS

• reputed company: $50-100/hr USD depending on experience
• Engagement: contract, project-based, with potential for ongoing work across multiple reputed company engagements

Location: work from reputed company, as long as your working hours substantially overlap one of the time zones above Possible travel to reputed company sites if needed Apply To This Job