Team: Engineering — AI Vertical

Experience: 5+ Years (incl. 2+ years shipping LLM systems in production)

Location: Mumbai - Andheri East

Reports to: Head of Engineering

Role Overview

Building agents that operate the CFO's function — accounts payable, month-end close and record-to-report, reconciliation, vendor and compliance workflows — end to end, within enterprise ERP environments. These systems execute finance processes rather than suggest actions: they interpret source documents, apply accounting and control logic, perform transactions in SAP, and escalate only genuine exceptions for human review.

Owns outcomes end to end rather than individual components; performance is measured through finance outcomes — touchless processing rate, exceptions per thousand documents, close cycle time and reduction in manual controller effort.

Key Responsibilities

Agents that run finance workflows

- Own end-to-end finance workflows as autonomous agents: invoice-to-pay, three-way matching and exception handling, GL close tasks, reconciliation, and vendor and compliance checks.
- Design tool and action surfaces over ERP systems, control flow, error recovery, human-in-the-loop checkpoints, approval and segregation-of-duty guardrails, and full auditability of every action taken on financial data.
- Build against production enterprise surfaces — SAP APIs, ERP user interfaces via computer-use agents, documents and file-based integrations — using LangGraph, LangChain or custom orchestration.

Memory and the finance knowledge graph

- Own agent memory: context management (windowing, summarisation, compaction), long-term memory, retrieval and forgetting policies, and cross-cycle state for long-running agents.




- Model the finance domain as a knowledge graph — vendors, invoices, POs, GRNs, GL accounts, contracts, approvals and their provenance — in a graph database (Neo4j or equivalent) alongside vector search.

Evaluation and model strategy

- Build and extend the evaluation platform: golden datasets, workflow-level metrics, regression gates in CI, automated judging calibrated against human review, and drift detection on live traffic.
- Work across model families (Anthropic, OpenAI, Google, open-weight) and own routing — which model handles which step at what quality, cost and latency point, with tiering, cascading and provider failover.

Scale and platform

- Own latency, throughput and unit economics for agents and pipelines operating at large document and transaction volumes, maintaining p50/p95/p99 latency and cost-per-workflow targets.
- Maintain the API surface (FastAPI, REST) that delivers these capabilities into the products, and mentor engineers working alongside AI systems.

Qualifications

- Degree in Computer Science, Computer Engineering, or a related field.
- Advanced proficiency in Python and modern AI/ML development practices.
- Hands-on experience with agent orchestration frameworks (LangGraph, LangChain, OpenAI Agents SDK), or with custom orchestration built on model APIs directly.




- Working knowledge of graph data modelling and a graph database (Neo4j, Neptune, ArangoDB): schema design, query (Cypher or Gremlin), and judgement on when a graph is preferable to a relational or vector store.
- Strong API and data engineering fundamentals (FastAPI, PostgreSQL, vector stores) and cloud-native deployment on GCP, AWS or Azure.
- Sound judgement on where LLM-based approaches are appropriate and where deterministic methods are preferable.
- Required experience: demonstrated multi-step agent in production with understood failure modes; memory/context strategy design; hands-on evaluation harness build; delivery on 2+ model providers with live migration experience; production LLM/ML system experience at scale with measurable before/after results.

Preferred / General Requirements

- Finance, accounting, audit or ERP (SAP) domain exposure, or a solid interest in developing domain depth.
- Computer-use or browser automation agents; GraphRAG and ontology design; document AI / OCR; fine-tuning or serving open-weight models.
- LLM tracing and observability (LangSmith, Langfuse, OpenTelemetry); enterprise AI security, governance and compliance frameworks.
- Regular use of AI coding agents in day-to-day development; a significant share of the codebase is authored this way.

Tech Stack

Python

- LangGraph / LangChain
- Anthropic, OpenAI and Google model APIs
- FastAPI
- PostgreSQL with pgvector
- Neo4j
- Elasticsearch
- Java/Spring Boot and React
- GCP and AWS
- Docker
- in-house evals platform and in-house

OCR. Skills: aws,finance,llm,google model apis,python,neo4j,openai,elasticsearch,langgraph,enterprise,orchestration,gcp,postgresql,fastapi,ai

📌 Senior AI Engineer (Mumbai)
🏢 Cognisol
📍 Mumbai