Senior LLM & AI Systems Engineer

At Algolight, we live and breathe the future of artificial intelligence and the physical world.

Our mission it two-folder:

On the civilian side, we build labeled 3D information layers from all types of sensors—for smart cities, drones, autonomous vehicles, infrastructure, public safety, and far beyond.
On the defense side, we bring true real-time intelligence to the edge—anywhere, for any sensor, at any point on the map—enabling smart, real-time decisions in the field.

Border Team Mission

At Algolight, we are building the next generation of autonomous, multi-sensor AI systems designed to operate in real, operational environments — not just in theory. Our work spans from raw sensor data to high-confidence triage, reasoning, and autonomous decision-making, enabling scalable, robust, and intelligent systems that reduce cognitive load on operators and help drive safer, more effective national operations.

As part of a national effort to modernize border operations, you will be a core technical force — helping define, design, implement, and scale AI-driven architectures that tie together data, models, agents, and operational systems.

As a Senior LLM & AI Systems Engineer, you will be responsible for designing, implementing, and owning the entire LLM / RAG / embedding stack used across the Border team.

🚀 What You’ll Be Responsible For

LLM System Architecture & Ownership

• Design and implement end-to-end LLM-based systems:
  from raw inputs to structured outputs used by humans and autonomous agents.
• Own how LLMs are used for:
  • scene understanding and summarization
  • context-aware reasoning
  • event explanation and triage
  • decision support and agent coordination

Retrieval-Augmented Generation (RAG)

• Build robust RAG pipelines over:
  • structured sensor events
  • time-series data
  • historical operational logs
  • knowledge graphs
• Design retrieval strategies:
  hybrid (vector + keyword), temporal, spatial, and context-aware retrieval.
• Handle long-context, partial information, and noisy inputs.

Embeddings, Search & Indexing

• Design and manage embedding pipelines for:
  • text
  • scene descriptions
  • structured events
  • multimodal representations (when applicable)
• Work with vector databases and search engines
• Optimize indexing, sharding, update strategies, and recall/latency trade-offs.

Multi-Modal & VLLM Systems

• Integrate vision-language models (VLMs / VLLMs) for:
  • image and video understanding
  • scene-to-text generation
  • cross-modal reasoning
• Combine outputs from perception systems (vision, radar) with LLM reasoning layers.

Agentic & Tool-Based LLM Workflows

• Design agent-based systems where LLMs:
  • call tools
  • query databases
  • reason over intermediate results
  • coordinate multi-step workflows
• Define tool schemas, context contracts, and memory strategies.
• Build systems that are deterministic where needed, not just probabilistic.

Performance, Reliability & Safety

• Optimize LLM pipelines for:
  latency, throughput, cost, and determinism.
• Implement guardrails:
  validation, confidence estimation, fallback logic.
• Ensure explainability and traceability of LLM outputs.

Deployment & Integration

• Deploy LLM systems in:
  • on-prem environments
  • edge-adjacent setups
  • hybrid cloud systems
• Integrate with existing AI, data, and autonomy platforms.
• Support shadow-mode runs, operational trials, and iterative rollout.

🔎 Data & Inputs You’ll Work With

• Scene descriptions from vision and radar systems
• Structured multi-sensor events and tracks
• Historical operational logs and annotations
• Knowledge graphs and geospatial context
• Images, video snippets, and temporal metadata

🎯 What We Are Looking For

Required Experience

• 5+ years of experience building production-grade AI or data systems.
• Deep hands-on experience with LLM-based systems beyond simple prompting.
• Proven experience implementing RAG pipelines end-to-end.
• Strong backend engineering skills.

Core Technical Skills

• Languages:
  Python (must), familiarity with C++ / Go is a plus.
• LLM Frameworks:
  LangChain, LlamaIndex, Haystack, or equivalent (deep usage, not tutorials).
• Models:
  Experience working with OpenAI, Anthropic, or open-source models (LLaMA, Mistral, Mixtral, Qwen, etc.).
• Vector Search:
  FAISS, Milvus, Weaviate, Pinecone, OpenSearch.
• Search & Retrieval:
  Elasticsearch / OpenSearch, hybrid search strategies.
• Multi-Modal Models:
  CLIP, BLIP, Flamingo, LLaVA, or similar.
• Infrastructure:
  Docker, Linux, APIs, async services.

⭐ Strong Advantages

• Experience building agentic systems in production.
• Background in knowledge graphs and structured reasoning.
• Experience with long-context handling and memory strategies.
• Familiarity with on-prem or restricted environments (no SaaS dependencies).
• Exposure to defense, autonomy, robotics, or mission-critical systems.

🌟 What Awaits You at Algolight

• Ownership of the reasoning layer of national-scale AI systems.
• Real-world constraints that force clean, thoughtful system design.
• Freedom to combine LLMs, retrieval, and classical systems the right way.
• Close collaboration with perception, radar, autonomy, data, and product teams.

A culture that values engineering rigor over hype.