Who we are:

Lifesight is a Unified Marketing Measurement platform that helps marketers make better decisions. Were a team of 130 serving 300+ customers across five offices: the US, Singapore, India, Australia, and the UK.

Were building the worlds best marketing intelligence and decisioning platform, and weve bet heavily on agentic AI to get there. MIA (our Marketing Intelligence Agent) is a production MMM measurement platform shipped as an agentic interface over the platform as well as remote MCP server and its already how our customers query causal models, run budget optimizations, and diagnose saturation and halo effects in natural language. This isnt an R&D; side project; its core product, and its growing fast.

Position overview:

Were looking for an Applied AI Engineer to own the execution of our agentic AI roadmap end-to-end, from agent harness and tool design through to evals, reliability, and the interactive experiences our agent surfaces to users. Youll work directly with the CTO and founding team on a system that already runs in production, not a greenfield prototype and not a research exercise.

This is a hands-on, majority-execution role: youll be writing the orchestration code, designing the MCP tools and extensions, building the evals that catch regressions before customers do, and shipping the UI surfaces (charts, curves, optimizers) that make the agents output legible.

What youll do:

- Design and build agentic workflows on top of MIAs MCP server - tool definitions, complex reasoning and multi-step planning, context/session management, and error recovery for a system real customers query daily.
- Own the harness quality bar: work with frontier models (Gemini, Claude and others) to close the gap between "technically works" and "production-grade agent behavior". Prompt/Skills/system design, reflection steps, structured tool responses, and graceful degradation when tools fail or return partial data.
- Build and maintain evaluation pipelines for agent quality. Accuracy, tool-call correctness, hallucination/fabrication detection, and regression testing across our causal models and workspaces.




- Extend the MCP surface: design new tools, metadata extensions, and (where relevant) interactive MCP App / UI resources; so agent output isnt just text but something a user can act on.
- Work with structured marketing data (BigQuery/Spanner-backed outputs and translate it into agent-consumable context and user facing narratives based on the users persona.
- Debug production agent issues systematically: stuck sessions, workspace binding failures, inconsistent tool outputs, model-vs-model disagreement and turn recurring failure patterns into fixes, not one-off patches.
- Stay current on the agentic AI and MCP ecosystem and bring back whats actually usable, new protocol capabilities, orchestration patterns, eval techniques; rather than chasing every new framework.

Youre a solid fit if you:

- Have 3-6 years of experience in ML/AI engineering, with recent hands-on work building and shipping agentic systems (not just RAG chatbots) - ideally something a real user depended on.
- Have built or deeply worked with MCP (Model Context Protocol), or a comparable tool-calling / function-calling framework, and understand the practical failure modes of agent-tool interaction.
- Are strong in Python, comfortable with LLM orchestration (whether via raw API tool-use, LangGraph, Claude Agent SDK, or your own harness), and know when NOT to reach for a framework.
- Have production experience with evals - you can articulate how youd measure whether an agent got better or worse after a prompt or tool change, and youve actually built that measurement, not just read about it.
- Are comfortable owning ambiguity: given a business use case (e.g. "help a marketer trust a budget reallocation"), you can scope it, prototype it,



and ship a v1 without needing a fully-specified spec.
- Have cloud deployment experience.

Nice to have:

- Familiarity with MCP Apps / interactive UI resources, or building agent-facing frontends (we use TanStack Query/Router, Zustand).
- Experience with vector databases and RAG, even if this role is more agentic-orchestration than retrieval-heavy.
- A track record of 0 to 1 builds; youve taken something from "nobodys built this yet" to "customers use this every day."

Our stack: GCP, Java and Python, BigQuery, Spanner, MCP (remote server + emerging MCP App/UI resource work), A2-UI, AG-UI, Claude/Anthropic APIs, ADK 2.0, Langgraph, Agno, VertexAI, and a Vite-based frontend (TanStack Query/Router, Zustand).

Whats in it for you:

- Ground-floor ownership of the agentic layer at one of the fastest-growing MarTech companies right now, your decisions on harness design and tool architecture ship to production customers within weeks, not quarters.
- Small, non-bureaucratic team with real empowerment; youll work directly with the CTO and founding engineers, not through three layers of process.
- A genuinely hard, well-scoped problem: agentic reasoning over causal marketing models, where correctness actually matters to the customers budget decisions.
- Competitive compensation and benefits, and a highly profitable, growing organization with real room to accelerate your career.
- A team that bonds over tea, movies, and Friday hangouts and takes work-life balance seriously.

Interested Wed rather see something youve built (an agent, an eval harness, an MCP tool, anything) than a polished resume - bring it along.

Required Skills

Google Cloud Platform (GCP) Framework Pragmatism Production LLM Evals ai AWS Model Context Protocol LLM Orchestration python Product Scoping & Design

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 Applied AI Engineer - Agentic Systems (Belagavi)
🏢 Lifesight
📍 Belagavi