Home/Jobs/Senior Forward Deployed Engineer I (AI Inference) Senior Forward Deployed Engineer I (AI Inference) DigitalOcean Bengaluru 6+ years Today $47.0K–60.2K/yr Full-time Hybrid Skills Required LLM inference vLLM llm-d TensorRT-LLM NVIDIA Dynamo Ray Serve SGLang Modular MAX Kubernetes Python Go gRPC Distributed systems GPU cloud KV-cache Description DigitalOcean is hiring a Senior Forward Deployed Engineer I focused on AI inference for high-growth startups and strategic AI enterprises. The role centers on building and optimizing cluster-scale LLM serving on GPU cloud infrastructure. It combines deep systems work with direct customer collaboration.

Company: DigitalOcean Role: Senior Forward Deployed Engineer I (FDE) Location: Bengaluru, India Experience 6+ years in AI/ML systems

6+ years of experience in Forward Deployed Engineering, AI Inference architect, or Technical Consulting roles supporting production AI systems

Ability to travel up to 30% for customer engagements, strategic workshops, conferences, and internal collaboration

Ability to consistently overlap with North American business hours, including availability until at least noon Eastern Time Responsibilities Act as AI Inference lead on the FDE team

Drive end-to-end design, development, and delivery of critical AI workloads

Architect and deploy production-grade, multi-tenant LLM inference engines

Embed alongside external tech leads to debug latency spikes and profile GPU memory utilization

Refactor inference code for high-concurrency production workloads

Solve distributed-systems problems unique to LLM serving

Implement strategies for prefill/decode disaggregation, KV-cache-aware routing, tiered prefix caching, and wide expert parallelism for MoE models





Guide customers on compute efficiency to improve tokens-per-second per dollar

Translate customer edge cases into reusable internal blueprints

Contribute performance fixes back to open-source inference ecosystems on behalf of DigitalOcean Additional Responsibilities Build internal tooling

Collaborate with customers, Product, Engineering, and go-to-market teams

Work directly with external engineering teams

Translate business latency SLAs into technical infrastructure solutions

Support strategic AI enterprises and high-growth startups

Operate at the intersection of distributed systems, specialized AI hardware, and customer impact

Own the full lifecycle of high-performance LLM deployment

Turn raw GPU compute into resilient serving infrastructure Nice To Have Hands-on experience with vLLM, llm-d, SGLang, TensorRT-LLM, or Modular MAX

Experience collaborating with GPU vendors, infrastructure providers, model vendors, or ecosystem partners on benchmarking, optimization, technical validation, or launch readiness

Preference for delivering production-ready code, low-latency container images, and deployment blueprints

Comfortable navigating fast-moving environments and tuning model workloads for diverse accelerator architectures More Skills distributed AI inference, LLM serving, continuous batching, paged attention, prefill/decode disaggregation, KV-cache-aware routing, tiered prefix caching,



wide expert parallelism, MoE models, tensor parallelism, data parallelism, quantization, FP8, FP4, specialized AI hardware, cluster-scale serving, GPU memory profiling, latency optimization Other The role is hybrid

DigitalOcean values growth mindset, thinking big and bold, and a scrappy ownership mentality The team emphasizes winning together, learning, having fun, and making a difference

Career development support includes reimbursement for relevant conferences, training, and education

Employees have access to LinkedIn Learning courses

Perks mentioned include Employee Assistance Program, local employee meetups, and flexible time off policy

Salary range is based on market data, relevant years of experience, and skills

Bonus eligibility may apply based on company and individual performance

Equity compensation may be provided, including equity grants upon hire and participation in the Employee Stock Purchase Program

DigitalOcean is an equal-opportunity employer

Application limit: maximum of 3 positions within any 180-day period Follow for Daily AI Tutorials Prepare for this role Recommended resources to build the skills for this position. Sponsored. Python for Everybody Specialization Coursera Learn Python from scratch — variables, data structures, web scraping, and databases. Python 3 Programming Specialization Coursera Intermediate Python covering classes, inheritance, APIs, and data processing.

Google Kubernetes Engine Specialization Coursera

Deploy and manage containerized AI applications at scale with GKE. More LLM inference jobs AI Engineer IC Markets Global Hyderabad 1 day ago Senior GenAI Engineer - VectorDBand MySQL HCLTech Pune 7 days ago

📌 Senior Forward Deployed Engineer I (AI Inference) (Bengaluru)
🏢 Top Gen AI Jobs
📍 Bengaluru