Responsibilities

· Build and operate the agentic loop: trigger → orchestration → agent execution → output to JIRA → human accept/reject → next agent, across design, coding, review, and testing agents.

· Implement model routing and retry logic across a provider-agnostic model layer (e.g., Claude via AWS Bedrock, self-hosted or alternative models as cost/sovereignty hedges), including business-continuity fallback if a given provider becomes unavailable.

· Own token cost control and context window management — per-agent and per-run budgets, circuit breakers that halt runaway execution, and cost observability tied back to JIRA.

· Stand up and maintain observability, alerting, and monitoring across the agent fleet (e.g., Langfuse or equivalent), so agent health, cost, and quality are visible in real time.

· Implement agent governance and safety guardrails: deterministic pre/post hooks gating every LLM call, kill switches, prompt injection prevention and mitigation, and audit logging.

· Integrate the harness with JIRA as the system of record and other business systems as needed, ensuring every agent action, decision, and human override is tracked with no side channels.

· Pair directly with client engineers throughout — this is capability transfer, not black-box delivery. You'll document, demo, and hand over as you build.

· Work in outcome-based delivery stages (spike → architecture sign-off → build → pilot) with gated milestones tied to working software demos, not fixed artifact checklists.





· Participate actively in team discussion and design decisions — this team expects engineers to challenge ideas constructively and speak up, not defer silently.

Must-Have Experience

· Hands-on production experience building agentic systems(not tutorial-level or personal-project experience.) Candidates should be able to speak concretely about systems they've shipped.

· Practical experience with agentic frameworks such as LangChain, LangGraph, or equivalent orchestration frameworks.

· Experience with LLM orchestration and model routing across multiple providers/models, including fallback and retry design.

· Working knowledge of agent governance: guardrails, human-in-the-loop approval flows, kill switches, and audit trails.

· Practical understanding of prompt injection risks and mitigation techniques.

· Experience with token cost management and context window/memory handling at production scale — this is a named governance requirement for the engagement, not a nice-to-have.

· Solid Python (or equivalent) engineering background, comfortable working in AWS environments (Bedrock/AgentCore exposure a strong plus).

· Experience with observability/monitoring tooling for distributed or agentic systems (e.g.,



Langfuse, Datadog, or equivalent).

· Comfortable working with JIRA/Atlassian APIs or similar ticketing-system-of-record integrations.

Nice to Have

· Direct experience with AWS Bedrock AgentCore, Temporal (or similar workflow orchestration), or LiteLLM-style model gateways.

· Exposure to Cursor or other AI-native IDEs in a production engineering context.

· Experience with self-hosted open-weight models (e.g., DeepSeek, GLM) as cost or sovereignty hedges alongside commercial APIs.

· Financial services or other regulated-industry background.

· Familiarity with Claude Code, Claude Cowork, or Claude Skills.

Qualifications

· Bachelor's degree in Computer Science, Engineering, or equivalent practical experience.

· 3-5+ years in software/platform engineering, with a meaningful portion of that time specifically on agentic or LLM-orchestration systems (not general ML or data engineering alone).

Relevant Experience

· Already built this kind of system and can talk through the trade-offs from experience, not theory.

· Comfortable operating with ambiguity - technology choices (frameworks, specific models, tooling) are expected to evolve during the engagementand milestones are tied to outcomes rather than fixed deliverables.

· Will contribute opinions - quiet execution without a point of view is not a fit for this team.

Skills:- AWS Bedrock, Agentic AI, Harness, Python, JIRA, LLM Evaluation Frameworks, IT governance and AgentCore,

📌 Sr Agentic Harness Engineer (Mumbai)
🏢 TGS The Global Skills
📍 Mumbai