Agent Application Engineer (Backend / Agentic AI) — Level 1

About SentiaflowSentiaflow is an AI engineering and IT services company building production-grade agentic AI systems, sitting at the intersection of LLMs and real business operations — data, APIs, permissions, workflow state, human decisions, security, and measurable outcomes. Our initial domain focus is healthcare, particularly clinical trials, where reliability, traceability, and clear human-decision boundaries matter more than a slick demo.Job DescriptionAs a Level 1 engineer, you'll implement bounded parts of a production agentic workflow under an Agent Captain or senior engineer, connecting models to application services, tools, data sources, and human approval points.You will:Translate a scoped business workflow into typed inputs, outputs, states, actions, and escalation pathsBuild backend services and tool integrations (Node.js/TypeScript or Python)Use LLMs only where model judgment adds value; keep rules, validation, authorization, and workflow control in deterministic codeDesign and validate structured model outputs before they touch downstream systemsHandle partial data, tool failures, duplicate events, retries, timeouts, rate limitsAdd logging, traces, metrics, and decision records for diagnosabilityWrite tests and evaluation cases that check whether the full workflow behaves correctly — not just whether output sounds fluentProtect sensitive data; participate in code, design, and release-readiness reviewsExplain implementation trade-offs clearly to engineers and stakeholdersSuccess in 6 months: own a bounded workflow module end-to-end, integrate models without letting probabilistic output bypass deterministic controls, produce release-ready evaluation evidence, and diagnose cross-boundary failures with less supervision.Desired SkillsApproximately 3–6 years hands-on backend/application engineering experience, with demonstrable hands-on work building agentic systems — not just calling an LLM API from a backend serviceLangGraph (or comparable agent orchestration framework) experience is required — building multi-step, stateful agent workflows with conditional branching, tool-calling loops, and recovery/retry logic, not a single-prompt wrapperDeep RAG experience, including:Chunking strategy design, embedding model selection, and retrieval evaluation (not just "connected a vector DB")Hybrid search (dense + sparse/keyword), re-ranking, and query rewriting/decompositionHandling retrieval failure modes: irrelevant context, stale data, contradictory sources, citation/grounding accuracyMeasuring RAG quality (precision/recall on retrieval, faithfulness/groundedness of generation) — not eyeballing outputsExperience designing agent state machines / workflow graphs: tool selection, planning loops, human-in-the-loop interrupts, checkpointing, and state persistence across long-running workflowsStrong programming in JS/TypeScript (preferred), Python, Java, C#, or GoSolid grasp of API design, databases, async processing, auth, testing, deploymentComfort reasoning about state, retries, idempotency, concurrency, permissions, audit trails, failure recoveryReal production debugging experience, not just greenfield buildsClear technical communicationWe're looking for engineers who've actually built and tuned agentic/RAG systems in production — not those who've only wired together frameworks or prompted an LLM API.Nice to have: experience with other orchestration frameworks (CrewAI, AutoGen, custom state machines), observability/eval tooling (LangSmith, Langfuse, custom trace pipelines), healthcare or regulated-industry background. Bachelors from IIT or NIT highly preferred.