Lead the design and delivery of AI context engineering and evaluation harness workstreams. Develop RAG, memory, token-management, ontology, MCP integration, sandboxing, orchestration, validation, and evaluation standards. Support pilot teams, define integrations with GitHub, Notion, and Slack, build YAML-based knowledge models and repo-native harness prototypes, and translate pilot evidence into company-wide best practices and technical standards.
The Context & Harness Committee is moving from strategy to execution. We are seeking three hands-on AI Tech Leads to define and validate our context engineering standards and evaluation harness before company-wide rollout.
Core responsibilities
- Lead the technical design and delivery of the assigned Context and Harness workstreams
- Review context formats, ontology models, harness proposals, and integration approaches.
- Support pilot teams across MFBS divisions with context conversion, fixture authoring, and evaluation.
- Define how GitHub, Notion, and Slack content maps into the agent context engine.
- Establish guidelines for federated context routing and token-budget allocation across sources.
- Contribute to an ontology proof of concept covering one domain and one workflow using YAML-based schemas.
- Validate integration with internal or external agent platforms, including access and smoke testing.
- Capture pilot evidence and contribute to the standard and company best-practices package.
Requirements
Required skills
Context engineering skills
- RAG and retrieval pipelines:Design advanced search and retrieval systems that supply models with accurate, relevant, and timely information.
- Context-window and token management:Compress conversation history, prioritize useful context, and filter noise to optimize model attention and cost.
- Memory architecture:Build short-term and persistent memory systems that allow agents to retain state across tasks and interactions.
- Instruction curation:Structure plain-English operating rules, Markdown files, domain guides, and other instructions for dynamic injection into agent tasks.
- Context formats and knowledge modeling:Design context layers and reusable knowledge assets using Markdown, YAML, schemas, and related formats.
Harness engineering skills
- Tool and MCP integration: Connect models to external APIs, execution environments, tools, and Model Context Protocol (MCP) servers.
- Sandboxing and permissions: Define safety boundaries, access controls, approval flows, and secure execution environments for agent actions.
- Validation and guardrails: Implement linters, automated tests, evaluations, and verification layers that detect hallucinations, policy violations, or broken code.
- Orchestration and control loops: Design multi-step workflows, retry logic, state transitions, and error-correction loops for long-horizon tasks.
- Evaluation harnesses: Build fixtures, benchmark tasks, quality gates, and CI-integrated evaluations using DeepEval, Promptfoo, or comparable frameworks
Supporting technical and leadership skills
- LLM and agent fundamentals: Strong understanding of agent workflows, RAG, evaluation methods, and quality gates for AI-generated output.
- Software engineering:Strong Git/GitHub and CI practices, experience with repo-native tooling, and the ability to prototype quickly.
- Technical leadership: Ability to make pragmatic architecture decisions, lead POCs, and turn evidence into reusable standards.
- Communication: Ability to write clear technical proposals and provide constructive cross-team review and feedback.
- Experience with ontology or knowledge modeling using YAML-based schemas.
- Familiarity with internal or external agent platforms.
- Experience with hybrid search, indexing pipelines, or context freshness mechanisms.
Success outcomes
- Context architecture, format, and evaluation standards are validated through representative pilots.
- Pilot teams can convert source knowledge and author evaluation fixtures using documented playbooks.
- A working repo-native harness POC demonstrates repeatable benchmark execution and quality gates.
- The committee has sufficient evidence to ratify the standard and decide whether to adopt or build the long-term harness.
Similar Jobs
Fintech • Professional Services • Consulting • Energy • Financial Services • Cybersecurity • Generative AI
Manage end-to-end transaction banking and retail payments projects within the BFSI sector, including compliance and regulatory initiatives. Lead Agile delivery, ISO 20022 payments projects, stakeholder communications across multiple geographies, release cycles, delivery management, RAID tracking, escalations, and senior stakeholder engagement. Mobile release management experience is preferred.
Top Skills:
AgileConfluenceIso 20022JIRA
Fintech • Professional Services • Consulting • Energy • Financial Services • Cybersecurity • Generative AI
Business Analyst responsible for payments and digital journey initiatives within retail and global banking. The role involves requirements elicitation, backlog and Agile delivery management, customer channel analysis, MVP prioritization, epics and user stories, stakeholder alignment, market and As-Is analysis, solution walkthroughs, implementation support, and coordination across business, technology, operations, risk, legal, compliance, and UX teams.
Top Skills:
ConfluenceJIRA
Fintech • Professional Services • Consulting • Energy • Financial Services • Cybersecurity • Generative AI
Business Analyst supporting payments and digital banking journeys for global retail banking clients. Responsibilities include requirements elicitation, backlog management, Agile delivery, customer channel analysis, MVP prioritization, Epic and user story creation, stakeholder coordination, As-Is analysis, market research, solution walkthroughs, and implementation support across business, technology, operations, risk, legal, compliance, and UX teams.
Top Skills:
Browser Front-End SolutionsConfluenceJIRAMobile Banking Applications
What you need to know about the Mumbai Tech Scene
From haggling for the best price at Chor Bazaar to the bustle of Crawford Market, the energy of Mumbai's traditional markets is a key part of the city's charm. And while these markets will always have their place, the city also boasts a thriving e-commerce scene, ranking among the largest in the region. Driven by online sales in everything from snacks to licensed sports merchandise to children's apparel, the local industry is worth billions, with companies actively recruiting to meet the demands of continued growth.
