Model Quality in Real-World Workflows Improving synthesis, summarization, grounding, and structured reasoning in a government contracting and proposal context.

Custom Evaluation and Feedback Loops Designing robust ways to evaluate relevance, completeness, hallucination risk, and user-centric performance.

Latency, Scale, and Control Balancing performance and cost across open and closed models while building a testbed for fine-tuning and long-context optimization.

Role

As a key member of the Vultron applied research team, you will:

• Build and improve model-powered product features that help federal contractors reason faster and act with confidence.
• Enhance grounding, summarization, and generation systems across Vultron’s modular proposal workflows.
• Develop and refine retrieval systems using RAG, vector search, and knowledge graphs.
• Design evaluation pipelines that go beyond BLEU or ROUGE — measuring utility, accuracy, and synthesis quality in noisy, complex documents.
• Work closely with federal domain experts to translate expertise into scalable model strategies.
• Conduct experiments with fine-tuning, synthetic data generation, and in-context learning to improve performance across retrieval and summarization tasks.

Qualifications Advanced LLM Applied Research Experience fine-tuning and prompting large models — particularly agentic or task-specific systems — and improving performance through grounding, context window optimization, or RAG.

Deep Expertise in AI Model Development Experience researching and building LLM-based systems, including both training and deployment.

Strong Publication Record Significant contributions to the AI field via top-tier conferences or open-source projects.

Excellent Communication & Collaboration Proven ability to work closely with engineers, product teams, and non-technical experts to ship fast and stay aligned.

Preferred Experience

• Ph.D. or MS in Computer Science, Machine Learning, or a related field (or equivalent industry experience).
• 5+ years of experience in ML research, applied LLMs, or model infrastructure.
• Experience with RAG pipelines and evaluation frameworks like RAGAS, DSPy, or LLaMAEval.
• Experience with scalable LLM systems using LangChain, LlamaIndex, Hugging Face, or similar frameworks.
• Experience designing or running fine-tuning experiments
• Familiarity with GPU-based experimentation and cloud model deployment (e.g., vLLM, DeepSpeed, Ray Serve).
• Prior work in high-trust domains is a plus.

Join us in shaping the future of government contracting with autonomy.