JPMorgan Chase·BFSI·22 hours ago
22 hours agoBe an early applicant
Software Engineer III - GenAI Foundational Services
Sign up free to see how well your resume matches this role.
What you'll do
- Execute creative software solutions, design, development, and technical troubleshooting for LLM-enabled applications and platforms.
- Design, build, and maintain backend services in Go, delivering secure, high-quality production code with strong testing discipline.
- Build gRPC services defined with Protobuf, including API design, schema evolution, and compatibility/versioning practices.
- Implement bidirectional streaming gRPC endpoints for LLM workloads (e.g., interactive sessions, token/partial-response streaming, incremental results, cancellations, backpressure/flow control).
- Integrate LLM services with supporting systems (authn/z, rate limits/quotas, caching, queues/streams, persistence) and partner with platform/SRE teams as needed.
- Review and debug SDK and service integrations; participate in code reviews and contribute to shared engineering standards.
- Instrument services with strong observability (metrics/logging/tracing), and contribute to runbooks and operational readiness (alerts, dashboards, on-call support as applicable).
- Identify recurring issues and contribute fixes and automation to improve reliability, latency, and operational stability.
- Add to the team culture of diversity, opportunity, inclusion, and respect.
What they're looking for
- Formal training or certification on software engineering concepts and 3+ years applied experience
- Proficiency in Go for backend/service development, including concurrency patterns (goroutines/channels), context usage, and performance troubleshooting.
- Working knowledge of Python for supporting services, internal tooling, automation, evaluation harnesses, or data/ETL tasks.
- Hands-on experience with gRPC and Protobuf in production, including API design and backward/forward compatibility considerations.
- Experience building and operating microservices/APIs with a production mindset (monitoring, debugging, incident support, and continuous improvement).
- Proficiency in automation and continuous delivery methods; strong unit/integration testing discipline.
- Proficient in secure coding practices and core SDLC activities (design, build, test, deploy, operate).
Nice to have
- Experience building LLM streaming experiences end-to-end (token/partial-response streaming, tool/function calling orchestration, session state management, safety/guardrail hooks).
- Familiarity with OpenTelemetry and tracing/metrics patterns for streaming RPCs (correlation IDs, span links, per-message metrics).
- Experience with Kubernetes/Docker and operating services in containerized environments.
- Messaging/streaming systems (Kafka/RabbitMQ/SQS), caching (Redis), and patterns for async orchestration alongside streaming.
- Security best practices for RPC systems: mTLS, authn/z, secrets management, secure-by-default API design, abuse prevention (rate limiting, payload limits).
- Understanding of cost management and spend alerting for AI/LLM workloads.
Summarised by NextRaise from the employer’s description, which follows in full below.
Full description from employer
We have an opportunity to impact your career and provide an adventure where you can push the limits of what’s possible.
As a Software Engineer III at JPMorganChase within the Chief Data and Analytics Office, you are an integral part of an agile team that works to enhance, build, and deliver trusted market-leading technology products in a secure, stable, and scalable way. You are responsible for contributing to critical technology solutions across multiple technical areas within various business functions in support of the firm’s business objectives—with a focus on Go-based backend services, gRPC/Protobuf, and bidirectional streaming to support LLM-enabled experiences.
Job responsibilities
- Execute creative software solutions, design, development, and technical troubleshooting for LLM-enabled applications and platforms.
- Design, build, and maintain backend services in Go, delivering secure, high-quality production code with strong testing discipline.
- Build gRPC services defined with Protobuf, including API design, schema evolution, and compatibility/versioning practices.
- Implement bidirectional streaming gRPC endpoints for LLM workloads (e.g., interactive sessions, token/partial-response streaming, incremental results, cancellations, backpressure/flow control).
- Integrate LLM services with supporting systems (authn/z, rate limits/quotas, caching, queues/streams, persistence) and partner with platform/SRE teams as needed.
- Review and debug SDK and service integrations; participate in code reviews and contribute to shared engineering standards.
- Instrument services with strong observability (metrics/logging/tracing), and contribute to runbooks and operational readiness (alerts, dashboards, on-call support as applicable).
- Identify recurring issues and contribute fixes and automation to improve reliability, latency, and operational stability.
- Add to the team culture of diversity, opportunity, inclusion, and respect.
Required qualifications, capabilities, and skills
- Formal training or certification on software engineering concepts and 3+ years applied experience
- Proficiency in Go for backend/service development, including concurrency patterns (goroutines/channels), context usage, and performance troubleshooting.
- Working knowledge of Python for supporting services, internal tooling, automation, evaluation harnesses, or data/ETL tasks.
- Hands-on experience with gRPC and Protobuf in production, including API design and backward/forward compatibility considerations.
- Experience building and operating microservices/APIs with a production mindset (monitoring, debugging, incident support, and continuous improvement).
- Proficiency in automation and continuous delivery methods; strong unit/integration testing discipline.
- Proficient in secure coding practices and core SDLC activities (design, build, test, deploy, operate).
Preferred qualifications, capabilities, and skills
- Experience building LLM streaming experiences end-to-end (token/partial-response streaming, tool/function calling orchestration, session state management, safety/guardrail hooks).
- Familiarity with OpenTelemetry and tracing/metrics patterns for streaming RPCs (correlation IDs, span links, per-message metrics).
- Experience with Kubernetes/Docker and operating services in containerized environments.
- Messaging/streaming systems (Kafka/RabbitMQ/SQS), caching (Redis), and patterns for async orchestration alongside streaming.
- Security best practices for RPC systems: mTLS, authn/z, secrets management, secure-by-default API design, abuse prevention (rate limiting, payload limits).
- Understanding of cost management and spend alerting for AI/LLM workloads.
BFSI
Company
JPMorgan ChaseBFSI
Mc Lean, United States of America
Company facts come from this company's own listings. We only show what the postings themselves carry.