AI Engineer · Agentic LLM Systems · Multi-Agent Infrastructure · Medical AI
Author of TrueNorth — I design, fine-tune, and ship production-grade AI systems end to end.
I build agentic AI systems — multi-agent pipelines, LLM infrastructure, on-device inference, and domain fine-tuning — and take them all the way to production.
- Open-source author — shipped TrueNorth to PyPI & NPM: an LLM infrastructure engine with 1,258 passing tests, a 13-stage safety pipeline, and 8-provider routing (~90% cost reduction).
- Fine-tuning at scale — published a 16-model medical AI suite (Qwen2.5) on Hugging Face: ICD-10/CPT/DRG coding, SNOMED mapping, clinical NLP, PM-JAY classification, and Hindi-medical. Each model trained with a QLoRA → DoRA → ORPO → merge pipeline on a real, paired SFT dataset (also published).
- Led a 10-person team across frontend, backend, and mobile — delivering two concurrent AI product lines.
- Hackathons — SANS FIND EVIL! (DFIR Automation) · Google Cloud Rapid Agent (GitLab Partner) · INDIA RUNS (Redrob AI × Hack2Skill, Data & AI).
- Research-grade rigor — published benchmarks (100% precision on SANS DFIR triage), open SFT datasets, and W&B-tracked training runs.
- Based in Bengaluru, India · Open to remote-first AI engineering roles (IST, comfortable with US/EU overlap).
| Project | What it does | Stack | Highlights |
|---|---|---|---|
| TrueNorth | Developer-first LLM infrastructure engine — declare the outcome in YAML, it owns the full multi-turn conversation lifecycle | Python · TS · Go · RN | 1,258 tests · 4 SDKs · hallucination firewall (94%) · 8-provider routing · PyPI + NPM |
| ShiftLeft | Autonomous 5-agent bug-fixing pipeline: reads repo → triages → generates fix → opens MR | Python · LangGraph · Gemini · GitLab MCP | End-to-end in ~60s, zero human steps · Google Cloud Rapid Agent Hackathon |
| LogPoseSIFT | Autonomous DFIR orchestrator — MCP server wraps 200+ SANS SIFT tools as typed Go endpoints | Go · Claude · Gemini · MCP · Volatility 3 | 100% precision · 92.8% recall · 0 hallucinations · SANS FIND EVIL! Hackathon |
| HireSignal | Ranks 100K candidates against a Senior AI Engineer JD in ~35s on CPU — multi-signal scoring + honeypot detection + semantic embeddings | Python · sentence-transformers · NumPy | No GPU, no API, no network during ranking · 85 honeypots caught · 10 tests · INDIA RUNS Hackathon |
| PocketLLM | 100% offline Android AI chat running LLMs on-device via MediaPipe C++ bridge | React Native · Expo · MediaPipe C++ · AWS S3 | 9 open-weight models (0.4–5.2 GB) · prompts never leave device |
| Medical AI Suite | 16 fine-tuned Qwen2.5 specialist models for medical coding, billing & clinical NLP | QLoRA · DoRA · ORPO · Unsloth · HF | 13 published models + 16 open SFT datasets · 2 live demos · Apache 2.0 |
Fine-tuned models live on Hugging Face · Training runs tracked on Weights & Biases
A suite of Qwen2.5 specialist models, one per clinical task. Each model is trained through a consistent QLoRA → DoRA → ORPO → merge pipeline (via Unsloth + TRL) on a dedicated, published SFT dataset — no synthetic training data. Released under Apache 2.0; training tracked on W&B.
📦 Collection: Medical AI Fine-tuned Model Suite · 📊 Datasets: AxisMapper Medical AI Suite
| Model | Size | Task | Dataset (rows) | Method | GPU |
|---|---|---|---|---|---|
| icd10-coder-qwen25-7b | 7B | Clinical text → ICD-10-CM code + justification | icd10-coder-sft (74.7k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| icd10-coder-qwen25-7b-merged | 8B | Merged full-weights build of the ICD-10 coder (no adapter load) | icd10-coder-sft (74.7k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| snomed-mapper-qwen25-7b | 7B | Clinical concept → SNOMED CT mapping | snomed-mapper-sft (74.7k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| clinical-summarizer-qwen25-7b | 7B | Clinical-note summarization | clinical-summarizer-sft (30k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| medical-billing-qwen25-3b | 3B | Medical billing code generation | medical-billing-sft (17k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| cpt-coder-qwen25-3b | 3B | Procedure text → CPT code | cpt-coder-sft (17k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| radiology-coder-qwen25-3b | 3B | Radiology report → diagnostic code | radiology-coder-sft (25.1k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| pmjay-classifier-qwen25-3b | 3B | India PM-JAY scheme package classification | pmjay-classifier-sft (11.1k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| discharge-qa-qwen25-3b | 3B | QA over discharge summaries | discharge-qa-sft (30k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| medical-ner-qwen25-3b | 3B | Clinical named-entity recognition | medical-ner-sft (16.7k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| hindi-medical-qwen25-3b | 3B | Hindi-language medical assistant | hindi-medical-sft (19.7k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| icd10-to-drg-qwen25-1b | 1.5B | ICD-10 → DRG for reimbursement grouping | icd10-to-drg-sft (5.39k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| insurance-classifier-qwen25-1b | 1.5B | CPT/HCPCS → Stark Law DHS classification | insurance-classifier-sft (1.6k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| ayurveda-icd-qwen25-1b | 1.5B | Ayurveda term → ICD mapping | ayurveda-icd-sft (3k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
| pharmacy-ner-qwen25-1b | 1.5B | Pharmacy / drug entity recognition | pharmacy-ner-sft (3.5k) | QLoRA → DoRA → ORPO → merge | A40 48GB |
Pipeline (all models): Qwen2.5-Instruct base → QLoRA SFT (4-bit NF4, rank 16, α 32) → DoRA → ORPO preference alignment → adapter merge. Optimizer paged_adamw_8bit · cosine 2e-4 · trained on RunPod (NVIDIA A40 48GB) via Unsloth + TRL. Per-model wall-time ranges from ~0.4 h (1.5B configs) to ~1.9 h (7B configs). Training tracked at wandb.ai/amareshhebbar-/axiomapper. Datasets built from authoritative real-world sources (e.g. CMS FY2026 ICD-10-CM, HCPCS Stark Law DHS list), not LLM-generated.
Live demos (Spaces): icd10-coder-demo · hiresignal
| Submission | Hackathon | Track | What it does |
|---|---|---|---|
| ShiftLeft | Google Cloud Rapid Agent | GitLab Partner | Label a GitLab issue → autonomous 5-agent pipeline reads the repo, triages the bug, writes the fix, and opens an MR in under 60 seconds |
| Poneglyphs — ShiftLeft | Google Cloud Rapid Agent | GitLab Partner | Label a GitLab issue shiftleft → 5-agent pipeline reads GitLab Orbit, triages, writes fix, opens MR |
| LogPoseSIFT | SANS FIND EVIL! | DFIR Automation | Autonomous DFIR orchestrator — deploys an AI crew via strict MCP endpoints, runs SIFT diagnostics, triages and self-corrects in seconds |
| AllBlue | SANS FIND EVIL! | DFIR Automation | Splunk alerts trigger autonomous AI forensic triage — IOC findings pushed back as structured events. 100% precision, 0 hallucinations |
| HireSignal | INDIA RUNS · Redrob AI × Hack2Skill | Data & AI Challenge | Ranks 100K candidates against a Senior AI Engineer JD in ~35s on CPU — multi-signal scoring, 85 honeypots detected, per-candidate reasoning. Live sandbox |
- Published TrueNorth to PyPI and NPM (Apache 2.0)
- Released a 16-model medical AI suite + 16 open SFT datasets on Hugging Face
- 1000+ problems solved on LeetCode
- B.E. Computer Science & Engineering, Dayananda Sagar College of Engineering (2021–2025)
Open to remote-first AI engineering roles — LLM infrastructure, agentic systems, fine-tuning, or AI product engineering.
Let's build something intelligent.