Senior Platform Engineer

This is a fully remote position, open to applicants in India.

📋 Description

• Develop the Agentic Platform as a product for internal teams, transforming frequently used team-built capabilities into streamlined processes with sensible defaults.

• Design, construct, and manage internal MCP servers while establishing standards for authentication, tool and schema design, versioning, testing, scaffolding, templates, and registry management.

• Create the platform layer for remote agents, encompassing deployment, scheduling, credentialing, observability, rate limiting, and decommissioning.

• Establish guardrails for autonomous agents, including defined permissions, human-in-the-loop approval processes, sandboxed execution, audit logging, spending controls, and blast-radius limitations.

• Act as the technical lead for retrieval-augmented generation patterns, vector stores, synchronization, and retrieval quality assurance.

• Oversee evaluation and observability for AI systems, including the development of evaluation harnesses, golden datasets, prompt versioning, and instrumentation.

• Enhance the agentic developer experience through the creation of internal plugins, skills libraries, code review agents, remediation agents, and migration tools.

• Expand and manage the Portkey LLM gateway, addressing provider and model coverage, routing, secure access, governance, PII monitoring, and cost attribution.

• Develop reference implementations and proofs of concept, subsequently handing them over to production teams.

• Set standards and playbooks, mentor engineers, provide guidance to leadership on build versus buy decisions, and participate in an on-call rotation.

⛳️ Requirements

• Bachelor’s degree in Computer Science, Engineering, or a related field (Master’s degree preferred).

• 8+ years of professional experience in software engineering.

• At least 2 years of experience in developing LLM-powered systems that have been deployed in production.

• Minimum of 2 years in a senior or technical lead position.

• Proficiency in production-grade Python.

• Strong familiarity with JVM, including the ability to confidently modify large Java or Kotlin codebases along with SBT, Maven, or Gradle build tools.

• TypeScript/Node.js experience is highly preferred.

• Practical MCP experience developing servers or clients, including tool and schema design and authentication processes.

• Experience in agent orchestration with LangGraph or a similar framework, covering context and state management.

• Demonstrated experience with production RAG, vector stores, embedding models, chunking, retrieval strategies, and incremental synchronization.

• Experience in evaluating non-deterministic systems using evaluation harnesses, regression suites, quality gates, and prompt versioning.

• Production experience with Claude Code or similar agentic coding tools.

• Strong security judgment for agentic systems, including defenses against prompt injection, sandboxed execution, scoped credentials, audit logging, and limiting blast-radius.

• Experience with Kubernetes and cloud platforms, ideally GCP, including GKE, IAM, GCS, Cloud SQL, Pub/Sub, and BigQuery.

• Familiarity with GitLab CI/CD, Terraform, Docker, and observability tools such as Datadog, Prometheus, and OpenTelemetry.

• Excellent written communication skills, with the ability to translate business challenges into reusable capabilities, proofs of concept, standards, and thoroughly tested code.

• Willingness to participate in an on-call rotation.

• Ability to overlap 2–3 hours with Pacific Standard Time core US business hours.

• Proven experience collaborating with US-based business teams.

• Outstanding written and verbal communication skills in English.

🏝️ Benefits

• Comprehensive coverage for health, life, and financial well-being.

• Medical insurance.

• Accident insurance.

• Retirement benefits.

• 12 company-paid holidays.

• 2 flexible holidays.

• Privilege/earned leave.

• Casual/sick leave.

• Paid maternity and paternity leaves.

• Weekly wellness events.

• Inclusive work culture.

• Ownership opportunities and impactful contributions.

• Individual opportunities for personal growth.