2 hours ago
Bengaluru, IndiaSenior
Responsibilities
- Extend LangGraph orchestrators and reusable agent components for routing, memory, tool-calling, delegation, checkpointing, and durable execution.
- Evolve APIs, tools, and MCP infrastructure with scalable concurrency, quotas, latency controls, caching, backward compatibility, and secure tool contracts.
- Expose contextual intelligence through APIs, tools, and MCP while improving retrieval, grounding, context assembly, and memory efficiency.
- Build LLM evaluation, tracing, analytics, regression, and release-gate capabilities measuring task success, tool-call accuracy, groundedness, latency, and cost.
- Implement tenant isolation, authorization, scoped credentials, runtime limits, and defenses against prompt injection, tool poisoning, excessive agency, and data leakage.
- Triage and debug customer issues across agents, tools, models, and downstream systems, and deliver root-cause fixes.
- Own multi-month cross-team projects, write design documents, review code and designs, mentor engineers, support technical customer and partner calls, and participate in on-call and incident response.
- Prototype developments in MCP, agent frameworks, and model capabilities and provide evidence-backed recommendations.
Requirements
- At least 5 years of experience building and running production software with strong distributed-systems fundamentals.
- At least 2 years of experience building production LLM-based systems, including agents used by real customers.
- Strong Python skills and production experience with LangGraph or an equivalent orchestration framework.
- Experience designing APIs and tool interfaces for LLM callers, including schemas, descriptions, error handling, and tool-selection behavior; direct MCP experience is strongly preferred.
- Experience scaling externally used APIs or platforms, including authentication, rate limiting, versioning, and backward compatibility.
- Production experience with retrieval, grounding, and running LLM evaluations.
- Experience with multi-tenant, security-sensitive cloud systems, preferably AWS, including authorization boundaries and data-leakage prevention.
- Experience debugging production issues across services and supporting customers directly or through support or solutions teams.
- Demonstrated ability to independently own multi-month cross-team projects and communicate with technical and non-technical audiences.
- Bachelor's degree in Computer Science, Engineering, or equivalent practical experience.
- Preferred experience includes production MCP servers, MCP open-source contributions, context from signals or knowledge graphs, external agent-platform integrations, agent interoperability protocols, B2B go-to-market or RevTech platforms, model routing, caching, cost and latency optimization, Kafka, Snowflake, Databricks, or Spark.
Benefits
- Health coverage, paid parental leave, paid time off, paid holidays, quarterly self-care days, and stock options.
- Equipment and support for working and connecting with teams at home or in one of the company's offices.
- Learning and development initiatives, including access to LinkedIn Learning.
- Quarterly wellness education sessions, wellness days, and ERG-hosted events.
- Full-time employee role with work-from-home or office work options.
Tech Stack
Categories
About 6sense
6sense builds a B2B revenue platform that uses intent data and AI to help marketing and sales identify in‑market accounts, run account‑based campaigns, and prioritize outreach. The company sells its software via SaaS subscriptions and integrates with common CRM and marketing automation tools. Founded in 2013 and headquartered in San Francisco, it is privately held and serves midmarket and enterprise B2B organizations.