AI Platform Engineer

Graviton Research Capital; Gurugram District; On-site; INR 2,800,000 - 6,000,000; Full time

Job summary

Graviton Research Capital is seeking a senior AI infrastructure engineer to build and operate internal AI platforms. You will deploy open-weight LLMs on internal servers and develop gateways between in-house and external models.

The role emphasizes on-prem deployment, performance tuning, model fine-tuning, and evaluating new models. Join a fast-paced team focused on high-scale AI systems and collaboration across product and research.

Qualifications

• 7+ years of engineering experience, preferably Python.
• Hands-on experience deploying and serving LLMs on on-prem servers.
• Knowledge of LLM gateways/proxies (LiteLLM, OpenRouter or in-house).
• Understanding of inference concepts: KV cache, batching, quantization, memory limits.
• Experience with fine-tuning and evaluation of tuned models.
• Strong interest in AI developments and recent models/techniques.

Responsibilities

• Deploy and operate open-weight LLMs on internal servers.
• Build and run an internal LLM gateway/router between in-house and external models.
• Size and manage internal infrastructure capacity across teams.
• Tune serving for throughput and latency (KV cache, batching, quantization, context-length).
• Evaluate new models and inference techniques; advise on adoption.
• Support fine-tuning of models on internal data and evaluate results.
• Help teams use the platform with coding assistants and retrieval over docs.

Skills

Python

LLM deployment

On-prem servers

LLM gateways

Inference optimization

Fine-tuning

AI trend awareness

Job description

Who are we: Graviton Research Capital is one of the largest quantitative trading firms emerging out of APAC, with a strong footprint across global exchanges and a rapidly growing presence across Europe and the USA. We’re long-term focused, and deeply invested in building high-performance teams that operate at scale in some of the most competitive markets globally. You will be part of the team that builds and manages AI platforms.

What you’ll do:

• Deploy and operate open-weight LLMs on our internal servers.
• Build and run an internal LLM gateway/router between in-house and external models.
• Size and manage internal infrastructure capacity across teams: scheduling, monitoring and utilization.
• Tune serving for throughput and latency: KV cache management, batching, quantization and context-length trade-offs.
• Evaluate new models and inference techniques as they appear, and advise on what to adopt.
• Support fine-tuning of models on internal data and help evaluate the results.
• Help teams use the platform with coding assistants, internal tools, retrieval over documentation.

What We’re Looking For:

• 7+ years of engineering experience, preferably in Python.
• Hands-on experience deploying and serving LLMs on on-prem servers.
• Experience with or strong working knowledge of LLM gateways/proxies (LiteLLM, OpenRouter or in-house).
• Understanding of inference concepts: KV cache, batching, quantization, memory limits.
• Working knowledge of fine-tuning and how tuned models are evaluated.
• Actively follows AI developments and can discuss recent models and techniques.

Why Join Us

• Work on challenging and advanced engineering problems
• Flat, engineering-centric culture with peers from strong technical backgrounds
• Fast paced decision-making, high ownership, and long-term focus
• Competitive compensation with strong growth opportunities