Role Overview The Senior AI Engineer designs, builds, and ships the agents that power OMAP: agent design, reasoning logic, tool integrations, and knowledge grounding, and then carries each one through to a live production deployment for individual clubs, chains, and franchise groups. The successful candidate owns the full technical arc of an agent's life, from capability design, through building and testing, to a live agent performing reliably against a real member base and meeting the outcomes clients contracted for.Key responsibilities

- Design and build agents from the ground up. Design the agent's reasoning flow, define its tool surface and function-calling logic, construct its retrieval and knowledge grounding pipeline, and engineer the prompts that govern its behaviour under real operating constraints.

- Ship agent implementations end to end. Configure and provision each agent, integrate it with the client's club management system, validate it through structured test conversations and calls, and promote it to production.

- Own post-launch performance. Review production transcripts and call recordings, identify where agent behaviour deviates from the intended outcome, and engineer the fix, whether that lives in prompt construction, tool definition, a knowledge gap, data mapping, or model configuration.

- Build and maintain client integrations. Develop Python connectors against external club management systems alongside CRM and messaging providers, and extend them as new capabilities are needed.

- Grow the shared agent runtime. Take requirements that recur across clients and build them into reusable platform capability, serving as a primary channel of input into the R&D; and Product functions.

- Engineer conversational and voice quality. For voice agents, design response latency budgets, interruption handling, and human transfer logic, all of which materially affect call completion rates.

- Represent engineering to clients. Contribute to scoping discussions, integration reviews,



and conversations that establish what an agent can appropriately do with member data.

Required qualifications

- Minimum 3 years of professional experience building and shipping production software, including 1 to 2 years working on LLM-backed systems that served real users in production.

- Advanced Python. FastAPI or an equivalent asynchronous web framework, asyncio, disciplined service layering, and meaningful test coverage using pytest.

- Applied LLM engineering. Designing agent reasoning flows, prompt design under operational constraints, tool and function calling, retrieval over client-supplied documents, and systematic evaluation of output quality beyond informal sampling.

- SQL and data modelling, specifically PostgreSQL. Demonstrated ability to interpret an unfamiliar schema of substantial size and establish how member, agreement, and payment records relate.

- Practical AWS experience. Lambda, S3, EventBridge, and IAM scoping, together with sound judgement when deployed behaviour diverges from local behaviour.

- Integration troubleshooting. A track record of diagnosing third-party API failures in production independently, using logs and request-level evidence.

- Disciplined use of Git within a peer-reviewed pull request workflow, and a consistent standard of maintainable, well-documented code.

- Strong written English. A significant portion of this role involves communicating technical constraints to non-technical stakeholders in writing.

Preferred qualifications

- Experience with voice AI platforms such as ElevenLabs or Twilio, or comparable realtime speech stacks, including familiarity with conversational latency budgets.

- Experience with Postgres, MongoDB, and Redis.

- Prior client-facing or forward-deployed engineering experience gained in an agency, professional services, or startup workplace with direct customer commitments.

- Domain familiarity with fitness, wellness, membership, or subscription retention businesses.

- Multi-tenant SaaS experience, including the security practices required for tenant isolation and the handling of customer personal data.

Work Location: In person

📌 AI Engineer (Ahmedabad)
🏢 DX Factor
📍 Ahmedabad